j-%dZddlmZddlmZddlmZddlmZddl m Z ddl m Z m Z ddlmZdd lmZmZmZdd lmZdd lmZdd Zed ddGddeZy)zLCombine documents by doing a first pass and then refining on more documents.) annotations)Any) deprecated) Callbacks)Document)BasePromptTemplateformat_documentPromptTemplate) ConfigDictFieldmodel_validator)BaseCombineDocumentsChain)LLMChainctdgdS)N page_contentz{page_content})input_variablestemplater s/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain/chains/combine_documents/refine.py_get_default_document_promptrs >*:EU VVrz0.3.1z1.0zThis class is deprecated. Please see the migration guide here for a recommended replacement: https://python.langchain.com/docs/versions/migrating_chains/refine_docs_chain/)sinceremovalmessagec`eZdZUdZded< ded< ded< ded< eeZd ed < d Zd ed < e dfd Z e ddZ e deddZe deddZ d ddZ d ddZd dZd!dZ d"dZe d#dZxZS)$RefineDocumentsChaina& Combine documents by doing a first pass and then refining on more documents. This algorithm first calls `initial_llm_chain` on the first document, passing that first document in with the variable name `document_variable_name`, and produces a new variable with the variable name `initial_response_name`. Then, it loops over every remaining document. This is called the "refine" step. It calls `refine_llm_chain`, passing in that document with the variable name `document_variable_name` as well as the previous response with the variable name `initial_response_name`. Example: .. code-block:: python from langchain.chains import RefineDocumentsChain, LLMChain from langchain_core.prompts import PromptTemplate from langchain_community.llms import OpenAI # This controls how each document will be formatted. Specifically, # it will be passed to `format_document` - see that function for more # details. document_prompt = PromptTemplate( input_variables=["page_content"], template="{page_content}" ) document_variable_name = "context" llm = OpenAI() # The prompt here should take as an input variable the # `document_variable_name` prompt = PromptTemplate.from_template( "Summarize this content: {context}" ) initial_llm_chain = LLMChain(llm=llm, prompt=prompt) initial_response_name = "prev_response" # The prompt here should take as an input variable the # `document_variable_name` as well as `initial_response_name` prompt_refine = PromptTemplate.from_template( "Here's your first summary: {prev_response}. " "Now add to it based on the following context: {context}" ) refine_llm_chain = LLMChain(llm=llm, prompt=prompt_refine) chain = RefineDocumentsChain( initial_llm_chain=initial_llm_chain, refine_llm_chain=refine_llm_chain, document_prompt=document_prompt, document_variable_name=document_variable_name, initial_response_name=initial_response_name, ) rinitial_llm_chainrefine_llm_chainstrdocument_variable_nameinitial_response_name)default_factoryrdocument_promptFboolreturn_intermediate_stepsc@t|}|jrg|d}|S)z2Expect input key. :meta private: intermediate_steps)super output_keysr&)self _output_keys __class__s rr*z RefineDocumentsChain.output_keysds. w*  ) )@\@+?@LrTforbid)arbitrary_types_allowedextrabefore)modec$d|vr |d|d<|d=|S)zFor backwards compatibility.return_refine_stepsr&r)clsvaluess rget_return_intermediate_stepsz2RefineDocumentsChain.get_return_intermediate_stepsts+ !F *289N2OF. /,- rcd|vr d}t||djj}d|vr%t|dk(r |d|d<|Sd}t||d|vrd|dd|}t||S) z4Get default document variable name, if not provided.rz"initial_llm_chain must be providedr!rzWdocument_variable_name must be provided if there are multiple llm_chain input_variableszdocument_variable_name z- was not found in llm_chain input_variables: ) ValueErrorpromptrlen)r5r6msgllm_chain_variabless r"get_default_document_variable_namez7RefineDocumentsChain.get_default_document_variable_name}s f ,6CS/ !$%89@@PP #6 1&'1,3Fq3I/0 9!o% , -5H H)&1I*J)KL;;N:OQ S/ ! rc 0|j|fi|}|jjdd|i|}|g}|ddD]I}|j||}i||}|jjdd|i|}|j |K|j ||S)aCombine by mapping first chain over all, then stuffing into final chain. Args: docs: List of documents to combine callbacks: Callbacks to be passed through **kwargs: additional parameters to be passed to LLM calls (like other input variables besides the documents) Returns: The first element returned is the single string output. The second element returned is a dictionary of other keys to return. callbacksr9Nr)_construct_initial_inputsrpredict_construct_refine_inputsrappend_construct_result r+docsrAkwargsinputsres refine_stepsdoc base_inputss r combine_docsz!RefineDocumentsChain.combine_docss$0//??,d$$,,KyKFKu 8C77SAK. .v.F/$''//N)NvNC    $  %%lC88rc`K|j|fi|}|jjdd|i|d{}|g}|ddD]Q}|j||}i||}|jjdd|i|d{}|j |S|j ||S7r7+w)aAsync combine by mapping a first chain over all, then stuffing into a final chain. Args: docs: List of documents to combine callbacks: Callbacks to be passed through **kwargs: additional parameters to be passed to LLM calls (like other input variables besides the documents) Returns: The first element returned is the single string output. The second element returned is a dictionary of other keys to return. rANr9r)rBrapredictrDrrErFrGs r acombine_docsz"RefineDocumentsChain.acombine_docss&0//??3D**33RiR6RRu 8C77SAK. .v.F6--66UUfUUC    $  %%lC88S Vs"5B.B*AB.B,*B.,B.c6|jrd|i}||fSi}||fS)Nr()r&)r+rLrKextra_return_dicts rrFz&RefineDocumentsChain._construct_results8  ) )!5| D %%%!# %%%rc^|jt||j|j|iSN)r!r r$r")r+rMrKs rrDz-RefineDocumentsChain._construct_refine_inputss/  ' 'd>R>R)S  & &  rc d|dji}|j|dj|jjDcic]}||| }}|j |jj di|i}i||Scc}w)Nrrr)rupdatemetadatar$rr!format)r+rHrI base_infok document_inforNs rrBz.RefineDocumentsChain._construct_initial_inputss $T!W%9%9: a))*262F2F2V2VW2VQIaL2V W  ' ')D)=)=)D)D)U})U )+((( Xs Bcy)Nrefine_documents_chainr)r+s r _chain_typez RefineDocumentsChain._chain_types'r)return list[str])r6dictrarrV)rHlist[Document]rArrIrratuple[str, dict])rLrbrKr rare)rMrrKr radict[str, Any])rHrdrIrrarf)rar )__name__ __module__ __qualname____doc____annotations__r rr$r&propertyr*r model_configr classmethodr7r?rOrRrFrDrBr` __classcell__)r-s@rrrs`0d /)QL*/4+O'S&+t+?  $L (#$(#$6 $999 9  9> $999 9  9:& ) ) )  )((rrN)rar )rj __future__rtypingrlangchain_core._apirlangchain_core.callbacksrlangchain_core.documentsrlangchain_core.promptsrr langchain_core.prompts.promptr pydanticr r r'langchain.chains.combine_documents.baserlangchain.chains.llmrrrrrrrzscR"*.-F877*W   Y K(4K(K(r